ig-harness-oss (Shudesu/ig-harness-oss) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 37 tools. No publisher has claimed this listing.

D
Caution
56/100

ig-harness-oss

IG Harness — OSS Instagram DM automation on Cloudflare Workers, with engagement gates, follow-up flows, and L Harness cross-linking.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

Shudesu

Source: github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 2 credentials: IG_HARNESS_API_KEY, INSTAGRAM_HARNESS_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes37 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

account_summary

Get a high-level summary of the Instagram account: follower count, active scenarios, recent broadcasts, tags, and forms. Use this to understand the current state before making changes.

broadcast

Send a broadcast DM to all followers, a specific tag group, or a filtered segment. Creates and immediately sends the broadcast.

bulk_apply_gates_to_reels

Create one engagement gate per reel ID in a single call, all referencing the same rich-message templates. Skips reels that already have a non-archived gate. Pass trigger_keyword=null for any-comment mode (most common for reels). Use list_recent_reels first to get reel IDs.

create_comment_rule

Create a comment rule that auto-sends a DM when someone comments on an Instagram post. Set postId to target a specific post, or leave null for all posts. Supports keyword matching or any comment trigger.

create_form

Create a form for collecting user responses. Can auto-tag responders and enroll them in scenarios.

create_media_post
create_rich_menu

Create a LINE rich menu with optional image upload. Provide imageData (base64) to attach the menu image in one step.

create_scenario

Create a step delivery scenario with multiple message steps. Each step has a delay and message content. Scenarios auto-trigger on dm_keyword (DM contains keyword), comment (post comment received), tag_added, or manual enrollment.

create_tracked_link

Create a click-tracking link. When clicked, can auto-tag the user and enroll them in a scenario.

enroll_in_scenario

Enroll an Instagram follower into a scenario. The follower will start receiving the scenario's step messages from step 1.

get_conversion_logs

View ad conversion send logs for a specific platform. Shows the history of conversion events sent to Meta CAPI, X, Google Ads, or TikTok, including status (sent/failed) and error details.

get_follower_detail

Get detailed information about a specific Instagram follower including tags, metadata, and profile.

get_form_submissions

Get all submissions for a specific form. Returns response data with timestamps and friend IDs.

get_friend_detail

Get detailed information about a specific friend including tags, metadata, and profile.

get_link_clicks

Get click analytics for a tracked link including total clicks and per-friend click history.

list_crm_objects

List all CRM objects of a specific type: scenarios, forms, tags, tracked links, broadcasts, or comment rules.

list_followers

List Instagram followers with optional filtering by tag or name search. Returns paginated results with follower details.

list_friends

List friends with optional filtering by tag, name search, or metadata values. Returns paginated results with friend details.

list_recent_reels

List the authenticated Instagram account's own reels (media_product_type=REELS). Returns id, caption, permalink, thumbnail_url, timestamp. Typically used to pick reel IDs for bulk_apply_gates_to_reels.

manage_ad_platforms

Manage ad platform integrations for conversion tracking. Supports Meta (Facebook/Instagram), X (Twitter), Google Ads, and TikTok. Use 'list' to see configured platforms, 'create' to add a new one, 'update' to modify settings, 'delete' to remove, or 'test' to verify the connection.

manage_broadcasts

配信の管理操作。list: 一覧、get: 詳細、create_draft: 下書き作成(送信しない)、update: 更新、send: 送信、send_to_segment: セグメント配信。

manage_comment_rules

Comment rule management operations. list: all rules, get: rule details, update: modify a rule, delete: remove a rule, toggle: activate/deactivate.

manage_engagement_gates

Engagement gate management. Actions: list (all gates), create (new gate), get (by id), update (patch), delete, list_deliveries (deliveries for a gate).

manage_followers

Follower management operations. count: get follower count, set_metadata: update metadata fields.

manage_forms

フォームの管理操作。list: 一覧、get: 詳細、update: 更新、delete: 削除。作成は create_form ツールを使用。

manage_friends

友だちの管理操作。count: 友だち数取得、set_metadata: メタデータ更新、set_rich_menu: リッチメニュー割当、remove_rich_menu: リッチメニュー解除。

manage_line_connections

LINE Harness multi-connection registry CRUD + diagnostics. Actions: list, create, update, delete, set_default, test, list_tracked_links, list_traffic_pools. `update` is the right way to rotate an api_key or fix a worker_url typo — the connection id is preserved, so every engagement_gate referencing

manage_media_posts
manage_rich_menus

リッチメニューの管理操作。list: 一覧取得、delete: 削除、set_default: デフォルト設定。作成は create_rich_menu ツールを使用。

manage_rich_messages

Manage reusable rich-message templates used by engagement gates. Actions: list, create, get, update, delete, test_send. Each rich message is a chain of blocks (text/image/card/carousel/quick_replies) dispatched sequentially to IG DM at send time. Use test_send to preview a message on your own IGSID

manage_scenarios

シナリオの管理操作。list: 一覧、get: 詳細(ステップ含む)、update: 更新、delete: 削除、add_step: ステップ追加、update_step: ステップ更新、delete_step: ステップ削除。

manage_staff

スタッフアカウントの追加・一覧・更新・削除・APIキー再生成。オーナー権限が必要です。

manage_tags

List, create, or delete tags, and add/remove tags to/from followers. Supports batch operations on multiple followers.

manage_tracked_links

トラッキングリンクの管理操作。list: 一覧、delete: 削除。作成は create_tracked_link ツールを使用。

send_dm

Send a DM to an Instagram follower. Supports text and image message types.

send_message

Send a text, image, or flex message to a specific friend. Use messageType 'image' for standalone image messages, 'flex' for rich card layouts.

upload_image

Upload an image to get a public URL for use in Instagram DMs and broadcasts. Accepts base64-encoded image data. Returns public URL.

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.12.1GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.12.1GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.12.1GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretIG_HARNESS_API_KEY
configIG_HARNESS_API_URL
🔐 secretINSTAGRAM_HARNESS_API_KEY
configINSTAGRAM_HARNESS_API_URL
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

37/37 tools missing one or more hints — account_summary (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); broadcast (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); bulk_apply_gates_to_reels (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +34 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

28/37 tool handlers declare input schemas (76%)

Declare an inputSchema with zod/joi/yup on every tool definition.

README present

No README found

Add a README.md describing the server and its tools.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Domain consistency

npm scope @ig-harness doesn't match GitHub owner shudesu

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 8 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/shudesu/ig-harness-oss?variant=verified)](https://m8ven.ai/mcp/shudesu/ig-harness-oss)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 188b6200f40fa3c3f3e9480eaddef2447f39ea8c
code hash: d6bc0abebe731ebf129b9639b66d66649c6fa6e78fcc16468dfcc735253eb8fa
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client